Predictive Data Analytics for Electricity Fraud Detection Using Tuned CNN Ensembler in Smart Grid

In the smart grid (SG), user consumption data are increasing very rapidly. Some users consume electricity legally, while others steal it. Electricity theft causes significant damage to power grids, affects supply efficiency, and reduces utility revenues. This study helps utilities reduce problems of theft, inefficient monitoring, abnormal in grids. To this end, an dataset from state corporation China (SGCC) is employed develops a novel model, mixture convolutional neural network gated recurrent unit (CNN-GRU), for automatic detection. Moreover, hyperparameters proposed model tuned using meta-heuristic method, cuckoo search (CS) algorithm. The class imbalance problem solved synthetic minority oversampling technique (SMOTE). clean trained then tested with classification. Extensive simulations performed based on real energy data. simulated results show that detection (CNN-GRU-CS) classification better than other approaches terms effectiveness accuracy by 10% average. calculated method 92% precision 94%.